Disclosure of Invention
The embodiment of the application provides a multi-factor crop yield estimation method, equipment and a medium, which are used for solving the technical problems that due to seasonal supply-demand contradiction of agricultural products, prices frequently change along with seasons, a production operator cannot accurately acquire supply-demand quotations of crops in advance, and the decision correctness of the production operator is directly influenced.
In one aspect, an embodiment of the present application provides a method for estimating yield of a multi-factor crop, including:
acquiring vegetation index data in a crop growth cycle of a research area, and preprocessing the vegetation index data serving as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area;
constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index values, model intercept and constants, and inputting the monthly average normalized vegetation index values of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area;
acquiring surface temperature data in the crop growth cycle of the research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area;
and correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, and obtaining a crop yield target value corresponding to the research area to realize the estimation of the crop yield.
In an implementation manner of the present application, the correcting the crop yield prediction value according to the monthly average surface temperature value and the monthly average rainfall, obtaining a crop yield target value corresponding to the research area, and implementing the estimation of the crop yield specifically includes:
acquiring a plurality of pieces of historical data corresponding to the research area, and screening out historical data corresponding to a monthly average earth surface temperature value and historical data corresponding to a monthly average rainfall from the plurality of pieces of historical data within a preset time interval;
determining the influence degree of the monthly average earth surface temperature value on the crop yield of the research area according to the historical data corresponding to the monthly average earth surface temperature value, and determining the influence weight coefficient of the monthly average earth surface temperature value on the crop yield of the research area according to the influence degree corresponding to the monthly average earth surface temperature value;
determining the influence degree of the average rainfall per month on the crop yield of the research area according to the historical data corresponding to the average rainfall per month, and determining the influence weight coefficient of the average rainfall per month on the crop yield of the research area according to the influence degree corresponding to the average rainfall per month;
and correcting the crop yield predicted value according to the influence weight coefficients corresponding to the monthly average earth surface temperature value and the monthly average rainfall and the influence weight coefficients corresponding to the monthly average rainfall, so as to obtain a crop yield target value corresponding to the research area, and realize the estimation of the crop yield.
In an implementation manner of the present application, the acquiring vegetation index data in the crop growth cycle of the research area specifically includes:
carrying out remote sensing inversion and monitoring on crops in a plurality of research areas through a medium-resolution imaging spectrometer, and obtaining remote sensing satellite data corresponding to the plurality of research areas;
and acquiring vegetation index data in the growth cycle of the crops in the research area based on the remote sensing satellite data corresponding to the research area.
In an implementation manner of the present application, the preprocessing the vegetation index data as the normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area specifically includes:
deriving a normalized vegetation index wave band in the vegetation index data, and splicing a plurality of framing images corresponding to the normalized vegetation index wave band into a panoramic image;
and calculating a monthly average normalized vegetation index value corresponding to the research area according to the panoramic image.
In one implementation of the present application, after deriving the normalized vegetation index waveband in the vegetation index data, the method further includes:
converting the data formats of the multiple framing images corresponding to the normalized vegetation index wave band into specified data formats;
and converting the projection coordinate system of the multiple framing images corresponding to the normalized vegetation index wave band into an appointed coordinate system, and deleting the boundary invalid value in the vegetation index data.
In one implementation of the present application, prior to constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index value, model intercept, and a constant, the method further comprises:
obtaining historical remote sensing satellite data corresponding to the research area, and determining historical target crop yield and historical monthly average normalized vegetation index value corresponding to the research area based on the historical remote sensing satellite data;
and determining a model intercept and a constant corresponding to the yield of the historical target crops obtained from the historical monthly average normalized vegetation index value according to the data relationship between the yield of the historical target crops and the historical monthly average normalized vegetation index value.
In an implementation manner of the present application, the obtaining of the earth surface temperature data in the crop growth cycle of the research area to obtain the monthly average earth surface temperature value corresponding to the research area specifically includes:
determining the earth surface temperature data of the research area in the crop growth cycle based on the remote sensing satellite data corresponding to the research area, and exporting earth surface temperature wave bands in the earth surface temperature data;
converting the data formats of the multiple amplitude images corresponding to the earth surface temperature wave band into specified data formats, and converting the projection coordinate systems of the multiple amplitude images corresponding to the earth surface temperature wave band into specified coordinate systems;
deleting the boundary invalid value in the earth surface temperature data, and splicing the plurality of the framing images in the specified coordinate system into a panoramic image;
and calculating a monthly average earth surface temperature value corresponding to the research area according to the earth surface temperature wave band corresponding to the panoramic image.
In an implementation manner of the present application, the acquiring rainfall data in a crop growth cycle of the research area to obtain a monthly average rainfall corresponding to the research area specifically includes:
acquiring rainfall data in a crop growth cycle of the research area based on remote sensing satellite data corresponding to the research area, and converting a data format of the rainfall data into a specified data format;
and counting the average rainfall per month of the research area according to the rainfall data in the specified data format, and determining the disaster condition corresponding to the research area according to the average rainfall per month.
In another aspect, an embodiment of the present application further provides a multi-factor crop yield estimation apparatus, including:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform:
acquiring vegetation index data in a crop growth cycle of a research area, and preprocessing the vegetation index data as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area;
constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index values, model intercept and constants, and inputting the monthly average normalized vegetation index values of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area;
acquiring surface temperature data in the crop growth cycle of the research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area;
and correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, and obtaining a crop yield target value corresponding to the research area to realize the estimation of the crop yield.
On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium, in which computer-executable instructions are stored, where the computer-executable instructions are configured to:
acquiring vegetation index data in a crop growth cycle of a research area, and preprocessing the vegetation index data serving as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area;
constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index values, model intercept and constants, and inputting the monthly average normalized vegetation index values of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area;
acquiring surface temperature data in the crop growth cycle of the research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area;
and correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, obtaining a crop yield target value corresponding to the research area, and realizing the estimation of the crop yield.
The embodiment of the application provides a multi-factor crop yield estimation method, equipment and medium, and at least comprises the following beneficial effects:
the method comprises the steps of obtaining a monthly average normalized vegetation index value of a research area by obtaining vegetation index data, constructing a prediction model corresponding to crop yield, and carrying out disaster assessment on crops in the research area by combining multiple factors of historical target crop yield, historical monthly average normalized vegetation index value, surface temperature data and rainfall data corresponding to the research area, so that the prediction error of the crop yield can be reduced, first-hand information data can be provided for operators in a futures market in time, the purpose that the operators want to obtain the supply and demand quotations of the crops in advance is met, the decision correctness of the operators is improved, and the method has a good practical application value. Moreover, the crop yield is actually evaluated by combining the historical data of a research area for years, so that the method and the device can be suitable for specific application scenes and can predict the yield according to local conditions.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a multi-factor crop yield estimation method, equipment and medium, wherein a monthly average normalized vegetation index value of a research area is obtained by obtaining vegetation index data, a prediction model corresponding to crop yield is constructed, and a plurality of factors including historical target crop yield, historical monthly average normalized vegetation index value, surface temperature data and rainfall data corresponding to the research area are combined to carry out disaster assessment on crops in the research area, so that the prediction error of the crop yield can be reduced, first-hand information data are provided for operators in a futures market in time, the purpose that the operators want to obtain supply and demand quotations of the crops in advance is met, the decision correctness of the operators is improved, and the method, the equipment and the medium have good practical application values. Moreover, the crop yield is actually evaluated by combining the historical data of a research area for years, so that the method and the device can be suitable for specific application scenes and can predict the yield according to local conditions. The technical problem that due to the existing seasonal supply and demand contradiction of agricultural products, prices change frequently along with seasons, a production operator cannot accurately acquire the supply and demand conditions of the agricultural products in advance, and the decision correctness of the production operator is directly influenced is solved.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the multi-factor crop yield estimation method provided in the embodiment of the present application includes:
101. and acquiring vegetation index data in the crop growth cycle of the research area, and preprocessing the vegetation index data serving as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area.
According to the demand of a production operator on the market, the remote sensing inversion and monitoring are carried out on the rainfall, the surface temperature, the crop growth and other information of any global food production area. The method comprises the steps of comprehensively influencing multiple factors of crop growth, combining historical contemporaneous crop yield monitoring results of a research area, and comparing current monitoring indexes with historical contemporaneous monitoring indexes, so that the yield of agricultural products is estimated, a first-hand evaluation report is provided for a production operator in the futures market, and the production operator is assisted in making a decision.
The surface temperature can be divided into canopy vegetation temperature and soil temperature, and under drought conditions, the water content of soil in bare land areas or areas with low vegetation coverage can be reduced, resulting in reduction of the heat capacity of the soil. Under the condition of solar radiation, the temperature of the soil with low specific heat capacity is faster to rise than that of the area with sufficient water, and the temperature is higher. And in the covered area, under the condition that the vegetation is lack of water, the air holes of the blades can be automatically closed under the stress of water, and when the root system of the vegetation is insufficient in water supply, the vegetation reduces the transpiration amount of water by closing the air holes of the blades, so that the temperature of the vegetation canopy is continuously increased. Therefore, the surface temperature can reflect the drought degree of the crops quickly and indirectly.
The absorption of chlorophyll energy in the vegetation can make plant leaf tissue have stronger absorption capacity to red light and blue light, and the cell at the back of the leaf and the sponge tissue cell at the middle part have stronger near-infrared reflection capacity. The vegetation index is an index constructed by utilizing data of remote sensing red light wave band and near infrared wave band, and can reflect the growth and health state of vegetation such as crops. Under the condition of water supply shortage, the growth of the vegetation is hindered, and the health state of the vegetation is changed, so that the health condition of the vegetation can be monitored through the vegetation index. The Normalized Difference Vegetation Index (NDVI) has a close relationship with the surface of the Vegetation leaf, and therefore, the Normalized Difference Vegetation Index NDVI is the most widely used Vegetation Index as a quantitative Index for measuring the health of the Vegetation.
In recent years, various meteorological disasters have been increasing, and large-scale commercial crop cultivation has been carried out in many areas to promote rapid economic progress, and the conventional crop cultivation has been gradually replaced. However, natural disasters, such as flood disasters and drought disasters, can cause damage to crops, affect crop yield, and bring significant economic loss to production operators. Therefore, the deep discussion of the agricultural meteorological disaster has important significance for ensuring the crop yield.
Drought disasters are caused by relatively little rainfall, which can cause a great deal of land loss and cracking, if the roots of crops cannot obtain enough water, the crops are difficult to grow or even stop normal growth, and drought climate disasters can cause crop yield reduction in drought areas and affect the crop yield in the areas. Flood disasters are caused by the fact that large-area water in a farmland is difficult to discharge in time due to long precipitation time, large water amount and short rainstorm time. In addition, the rising of river water causes the yield reduction of a large amount of crops, and the amount of rainfall has a very important influence on the crop yield. Thus, the present application incorporates rainfall data into an important impact factor for crop yield assessment.
Before estimating the crop yield, the vegetation index MOD13Q1 data of a research area in a crop growth cycle need to be acquired, the vegetation index MOD13Q1 data is used as normalized vegetation index NDVI data in a corresponding time period of the growth cycle, and then the server preprocesses the normalized vegetation index NDVI data so as to obtain a monthly average normalized vegetation index value corresponding to the research area.
Specifically, the server carries out remote sensing inversion and monitoring on crops in a plurality of research areas through a medium resolution imaging spectrometer MODIS, obtains remote sensing satellite data corresponding to the plurality of research areas, and then obtains vegetation index MOD13Q1 data in the growth cycle of the crops in the research areas based on the remote sensing satellite data corresponding to the research areas.
The server exports the normalized vegetation index NDVI wave band in the vegetation index data, and the data format of the normalized vegetation index NDVI wave band is hdf format, and the data format of the normalized vegetation index NDVI wave band needs to be converted into a specified data format from the hdf format. It should be noted that the format of the prepared data in the embodiment of the present application is the tif format.
Then, the server also needs to convert projection coordinate systems of the multiple framing images corresponding to the normalized vegetation index NDVI wave band into designated coordinate systems, splice the multiple framing images corresponding to the normalized vegetation index NDVI wave band into panoramic images through raster data in a large-area research area, and then cut the panoramic images according to the research area.
The server deletes the boundary invalid value in the vegetation index data, determines an initial value of the panoramic image, calculates normalized vegetation index data corresponding to the panoramic image of the research area according to the initial value of the panoramic image, and then calculates a monthly average normalized vegetation index value corresponding to the research area according to a plurality of amplitude-divided images corresponding to the panoramic image. The formula is as follows:
it should be noted that g in this embodiment of the application is an initial value of the panoramic image, h is normalized vegetation index data after the band operation, a data range of the normalized vegetation index data is between 0 and 1, and if the normalized vegetation index data is closer to 1, it indicates that the growth vigor of the corresponding crop is better and more dense.
The server counts the monthly average normalized vegetation index values corresponding to all crops in the research area according to the area corresponding to the crops, and arranges the normalized vegetation index data of the crops in the research area and the monthly average normalized vegetation index values in the research area into corresponding Excel tables for subsequent checking, and the normalized vegetation index data can also be used as a historical data source for subsequent crop yield prediction.
102. And constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index values, model intercept and constants, and inputting the monthly average normalized vegetation index values of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area.
The server constructs a prediction model through the historical target crop yield, the historical monthly average normalized vegetation index value, the model intercept and the constant, the historical monthly average normalized vegetation index value is used as an independent variable, the historical target crop yield of a research area is used as a dependent variable, the confidence interval of the prediction model is set to be 95%, and a formula corresponding to the prediction model is obtained as follows:
in the embodiment of the present application, a is a model intercept, b is a constant, x is a monthly average normalized vegetation index value of the crops in the research area, and y is a predicted value of the yield of the crops in the research area.
And the server inputs the calculated monthly average normalized vegetation index value of the research area into the prediction model, so that the crop yield prediction value corresponding to the research area can be obtained.
In an embodiment of the application, before constructing a prediction model composed of historical target crop yield, historical monthly average normalized vegetation index value, model intercept and constant, a server needs to obtain historical remote sensing satellite data corresponding to a research area, determine historical target crop yield and historical monthly average normalized vegetation index value corresponding to the research area based on the historical remote sensing satellite data, determine a data relationship between the historical target crop yield and the historical monthly average normalized vegetation index value, and determine the model intercept and the constant corresponding to the historical target crop yield obtained by the historical monthly average normalized vegetation index value according to the data relationship between the historical target crop yield and the historical monthly average normalized vegetation index value, so that each component in the prediction model can be determined.
103. And acquiring surface temperature data in a crop growth cycle of the research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area.
Specifically, the server determines the data of the earth surface temperature MOD11A2 of the research area in the crop growth cycle based on the remote sensing satellite data corresponding to the research area, takes the earth surface temperature data as the earth surface temperature data in the time period corresponding to the growth cycle, and then preprocesses the earth surface temperature data to obtain the monthly average earth surface temperature value corresponding to the research area.
The server exports the earth surface temperature wave band in the earth surface temperature data, the data format of the earth surface temperature wave band is hdf format, and the earth surface temperature wave band needs to be converted into the appointed data format from hdf format. It should be noted that the format of the prepared data in the embodiment of the present application is the tif format.
The server also needs to convert projection coordinate systems of the multiple amplitude images corresponding to the earth surface temperature wave band into designated coordinate systems, perform image splicing on a large-area research area to obtain a panoramic image, and then cut the panoramic image according to the research area to obtain a cut image. And then, deleting the boundary invalid value in the earth surface temperature data by the server, and calculating the monthly average earth surface temperature value corresponding to the research area according to the earth surface temperature wave band corresponding to the cutting image in the specified coordinate system. The formula is as follows:
it should be noted that the thermodynamic temperature T in the examples of the present application is expressed in units of Kelvin (Kelvin), abbreviated as kai, and denoted by K, and T is degrees celsius.
Then, the server counts the monthly average surface temperature values corresponding to all crops in the research area according to the areas corresponding to the crops, and arranges the surface temperature data of the crops in the research area and the monthly average surface temperature values in the research area into corresponding Excel tables for subsequent checking, and the monthly average surface temperature values can also be used as a historical data source for subsequent crop yield prediction.
The server obtains rainfall data in a crop growth cycle of a research area through remote sensing satellite data corresponding to the research area, the data format of the rainfall data is nc4 data format, and the data format of the rainfall data needs to be converted into a specified data format by the server. It should be noted that, in the embodiment of the present application, the specified data format is a txt data format.
After the server converts the rainfall data from the nc4 data format to the txt data format, the server also needs to count the average rainfall capacity of the research area per month, and determines the disaster condition corresponding to the research area according to the average rainfall capacity of the research area per month. It should be noted that the average monthly rainfall in the embodiment of the present application is used to indicate how much rainfall is in the research area.
104. And correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, and obtaining a crop yield target value corresponding to the research area to realize the estimation of the crop yield.
Specifically, the server can obtain a plurality of pieces of historical data corresponding to the research area from an Excel table of the research area every year, so that the historical data corresponding to the monthly average earth surface temperature value and the historical data corresponding to the monthly average rainfall within a preset time interval can be screened out from the plurality of pieces of historical data. Then, the server determines the influence degree of the monthly average surface temperature value on the crop yield of the research area according to the historical data corresponding to the monthly average surface temperature value, and determines the influence weight coefficient of the monthly average surface temperature value on the crop yield of the research area according to the influence degree corresponding to the monthly average surface temperature value. Meanwhile, the server determines the influence degree of the average rainfall per month on the crop yield of the research area according to the historical data corresponding to the average rainfall per month, and determines the influence weight coefficient of the average rainfall per month on the crop yield of the research area according to the influence degree corresponding to the average rainfall per month.
The server corrects the crop yield predicted value according to the influence weight coefficients corresponding to the monthly average earth surface temperature value and the influence weight coefficients corresponding to the monthly average rainfall and the monthly average rainfall, so that a crop yield target value corresponding to a research area can be obtained, and the crop yield is estimated.
The problem of be difficult to obtain in batches the normalization vegetation index and the earth's surface temperature inversion of research regional scope crops is solved in this application, the research uses multiple outside remote sensing data source, construct the prediction model of crop output according to actual conditions, IMERG rainfall data is downloaded according to the research area, the problem of preliminary treatment, combine the multifactor that influences crop output, carry out calamity evaluation to crop output prediction model result, can be according to local conditions carry out the prediction of crop output, the blank of the comparatively accurate output prediction of economic crop in the futures market has been solved, can improve the accuracy of crop output estimation, and then better provide crops supply and demand conditions for the production operator in the futures market.
Fig. 2 is a schematic flow chart of another multi-factor crop yield estimation method according to an embodiment of the present disclosure. As shown in fig. 2, the present application is illustrated with us soybean crop yield estimates from 8 months to 11 months from 2019 to 2022.
Firstly, a server downloads vegetation index MODIS13Q1 data in a research area, preprocesses the vegetation index MODIS13Q1 data, derives normalized vegetation index NDVI wave bands in the MODIS data, converts data formats corresponding to the normalized vegetation index NDVI wave bands into specified data formats, converts a projection coordinate system corresponding to an original image into a specified coordinate system, performs image splicing and cutting operation on a plurality of sub-images according to the research area, deletes invalid boundary values in the vegetation index MODIS13Q1 data, further calculates normalized vegetation index NDVI wave bands, converts the NDVI values into a value range from-1 to +1, counts monthly average normalized vegetation index NDVI values corresponding to soybean crops in the research area in a sub-area mode, and arranges the normalized vegetation index NDVI data and the monthly average normalized vegetation index NDVI values into an Excel table.
Secondly, the server takes the crop yield of the research area as a dependent variable, takes the normalized vegetation index NDVI data as an independent variable, and sets the confidence interval of the prediction model to be 95%, so that the formula for obtaining the prediction model is as follows:
it should be noted that in the examples of the present application, y is the crop yield, x is the monthly average normalized vegetation index NDVI value of the crop, and a is equal to
Is the model intercept, b equals >>
Is a constant.
The server inputs the average normalized monthly vegetation index NDVI value of the crops in the growth period as an independent variable into the formula, so that the crop yield predicted value corresponding to the research area can be obtained.
The third step: the server downloads surface temperature MODIS11A2 data in a research area, preprocesses the surface temperature MODIS11A2 data, exports surface temperature wave bands in the MODIS data, converts data formats and projection types, performs image splicing and cutting operation on a plurality of amplitude images according to the research area, removes boundary invalid values in the surface temperature data, calculates the surface temperature wave bands, converts surface temperature data units from Kelvin to centigrade degrees, performs partition statistics on surface temperature average values, and arranges the surface temperature data and monthly average surface temperature values of the research area into an EXCEK table.
The fourth step: the server downloads IMERG rainfall data in a crop growth period, converts the rainfall data from a.nc 4 data format into a.txt data format, calculates the average rainfall per month corresponding to a research area, and arranges the rainfall data and the average rainfall per month corresponding to the research area into an Excel table.
The fifth step: and the server carries out disaster evaluation, takes the surface temperature data and the rainfall data as correction factors for monitoring the crop yield, carries out grade division and weight calculation on the disasters by researching the influence of various disasters in the long-sequence historical data on the crop yield according to the crop planting technology and system in the research area, and corrects the predicted crop yield value output by the prediction model based on the surface temperature data and the rainfall data. The us soybean disaster impact is shown in table 1:
table 1: influence value of rainfall disaster of American soybean
Through data investigation, the disasters of the American soybean influencing the yield in the growth cycle are mainly drought and flood disasters caused by rainfall. Moreover, disaster evaluation is performed on soybean crops in consideration of the advanced technology of agriculture in the United states and the like. By referring to the relevant data and combining the actual situation, the disaster evaluation rule is determined as follows:
drought mainly occurs in 6, 7 and 8 months, when drought occurs in a month, the yield of soybeans influences from the next month, and whether the drought or flood disaster occurs is mainly determined according to the list of the table.
The method selects the years close to the disaster years for disaster reference and overall evaluation, the percentage of the crop yield influenced by the disaster is weighted according to the percentage of the crop yield of the years close to the disaster, namely w. The difference between the predicted crop yield value and the actual crop yield value of the selected disaster-affected year in 8 months is determined as the yield influence, namely v. And calculating the influence of the fully-affected yield of the selected affected year, namely c1. The formula is as follows:
c1=v/w
according to the method, the disaster-affected yield ratio w1 of the current year is determined through rainfall data, and v1 is calculated.
v1=w1*c1
FIG. 3 is a line graph showing the error between predicted and actual yield per US soybean unit provided in the examples of the present application. In 2018, the error value between the predicted value and the actual value of the yield of the soybean crops in unit area is 0.410 bushels/acre, in 2019, the error value between the predicted value and the actual value of the yield of the soybean crops in unit area is 0.550 bushels/acre, in 2020, the error value between the predicted value and the actual value of the yield of the soybean crops in unit area is 0.600 bushels/acre, in 2021, the error value between the predicted value and the actual value of the yield of the soybean crops in unit area is 0.600 bushels/acre, and in 2022, the error value between the predicted value and the actual value of the yield of the soybean crops in unit area is 0.800 bushels/acre.
The results of the above examples show that the prediction model is constructed based on the normalized vegetation index NDVI data, crop yield prediction is performed by combining historical data of a research area, and disaster assessment is performed by combining a plurality of image factors, so that the predicted crop yield error is small, the first-hand crop request market is provided for production operators in the futures market in time, and the method has a good practical application value.
In the method, the disaster assessment is actually performed by combining the historical data for many years, so that the method is suitable for specific application scenes and can predict the yield according to local conditions. Meanwhile, batch production is realized in each link in the method, the method can be better operated in commercialization, and the timeliness is ensured.
It should be noted that the method shown in fig. 2 is substantially the same as the method shown in fig. 1, and therefore, portions that are not described in detail in fig. 2 may specifically refer to the related description in fig. 1, and are not described herein again.
The above is the method embodiment proposed by the present application. Based on the same inventive concept, the embodiment of the present application further provides a multi-factor crop yield estimation device, the structure of which is shown in fig. 4.
Fig. 4 is a schematic diagram of an internal structure of a multi-factor crop yield estimation apparatus according to an embodiment of the present disclosure. As shown in fig. 4, the apparatus includes:
at least one processor;
and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform:
acquiring vegetation index data in a crop growth cycle of a research area, and preprocessing the vegetation index data serving as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area;
constructing a prediction model consisting of historical target crop yield, a historical monthly average normalized vegetation index value, a model intercept and a constant, and inputting the monthly average normalized vegetation index value of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area;
acquiring surface temperature data in a crop growth cycle of a research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area;
and correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, and obtaining a crop yield target value corresponding to the research area to realize the estimation of the crop yield.
An embodiment of the present application further provides a non-volatile computer storage medium, which stores computer-executable instructions configured to:
acquiring vegetation index data in a crop growth cycle of a research area, and preprocessing the vegetation index data serving as normalized vegetation index data in the growth cycle to obtain a monthly average normalized vegetation index value corresponding to the research area;
constructing a prediction model consisting of historical target crop yield, historical monthly average normalized vegetation index values, model intercept and constants, and inputting the monthly average normalized vegetation index values of the research area into the prediction model to obtain a crop yield prediction value corresponding to the research area;
acquiring surface temperature data in a crop growth cycle of a research area, acquiring a monthly average surface temperature value corresponding to the research area, acquiring rainfall data in the crop growth cycle of the research area, and acquiring monthly average rainfall corresponding to the research area;
and correcting the crop yield predicted value according to the monthly average earth surface temperature value and the monthly average rainfall, obtaining a crop yield target value corresponding to the research area, and realizing the estimation of the crop yield.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the device and media embodiments, the description is relatively simple as it is substantially similar to the method embodiments, and reference may be made to some descriptions of the method embodiments for relevant points.
The device and the medium provided by the embodiment of the application correspond to the method one to one, so the device and the medium also have the similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device and the medium are not repeated herein.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.